UI-Mate 27B on NVIDIA Jetson AGX Thor (128 GB)

Can the NVIDIA Jetson AGX Thor (128 GB) run UI-Mate 27B?

Yes, it runs well

Runs well. At Q5_K_M it needs about 29.8 GB of 115 GB usable, with an estimated speed of 10.1 tok/s.

Best quant: Q5_K_M
Generation speed: 10.1 tok/s
Prompt processing: 211 tok/s
First token (1K prompt): 4.9 s
Largest safe context: 256K

Best app to run it on the NVIDIA Jetson AGX Thor (128 GB)

On Linux on ARM boards

vLLM

Inference server · runs on vLLM

The full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.

vllm serve tencent/UI-Mate-27B

LM Studio Point-and-click: search, download and chat in one window.
llama.cpp Usually the first to support new model architectures.

Want an agent? UI-Mate 27B supports tool use, so you can pair a llama.cpp or MLX LM server with one of these. Apps that run on this computer come first.

Coding agents

Personal assistants

How we choose: the files published for this model, your operating system and GPU, whether it fits fully in memory, and published speed tests (MLX vs llama.cpp on Apple silicon, vLLM vs llama.cpp vs Ollama on NVIDIA). Details.

Download UI-Mate 27B

Recommended for the NVIDIA Jetson AGX Thor (128 GB): Q5_K_M. Every other quantization has its own download link in the table below.

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

Download the Q5_K_M file (opens in a new tab)

huggingface.co/bartowski/tencent_UI-Mate-27B-GGUF (opens in a new tab)

ollama run hf.co/bartowski/tencent_UI-Mate-27B-GGUF:Q5_K_M

Original weights · Hugging Face

Full-precision files from Tencent, for fine-tuning, vLLM, Transformers.

huggingface.co/tencent/UI-Mate-27B (opens in a new tab)

No sign-in needed.

Links checked 3 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 83Great quality (A) · 83 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q5_K_M, from its editorial quality tier scaled by the quantization or precision. It’s the same on any hardware that runs this variant. Scale: A+ 85+ · A 70+ · B 55+ · C 40+ · D under 40.
Runs Runs well: How well it runs on the NVIDIA Jetson AGX Thor (128 GB): speed, capped by how well it fits in memory. Runs great: 30+ tokens/s (or near the image, video or decision speed target) · Runs well: 10+ tokens/s · Slow: 3+ tokens/s · Very slow: under 3 · Won’t run: doesn’t fit even with offload. A tight fit or RAM offload caps it at Runs well; heavy offload caps it at Slow.

Match score

To order lists, each result also gets a match score out of 100 from four parts. It favors the most capable model that still runs well.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.	37.5 / 45
Memory fitFull marks when the model fits in the share of unified memory the GPU can use; fewer when it goes past that limit.	25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	7.5 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	6.0 / 15
Match score	76.0 / 100

The match score orders results; it is not shown as a grade. Quality and Runs are the two ratings in the tables.

Every quantization on the NVIDIA Jetson AGX Thor (128 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	21.3 GB	115 GB	20.1 tok/s	Runs well	60Good quality (B) · 60 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q3_K_M`	23.8 GB	115 GB	15.8 tok/s	Runs well	72Great quality (A) · 72 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4_K_M`	27.0 GB	115 GB	12.2 tok/s	Runs well	81Great quality (A) · 81 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	29.8 GB	115 GB	10.1 tok/s	Runs well	83Great quality (A) · 83 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	32.8 GB	115 GB	8.5 tok/s	Slow	85Excellent quality (A+) · 85 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	39.4 GB	115 GB	6.2 tok/s	Slow	86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	65.1 GB	115 GB	2.9 tok/s	Very slow	86Excellent quality (A+) · 86 of 100: how capable the model is at F16, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab) Original weights (opens in a new tab)

Memory figures assume 8K of context. Longer conversations or documents grow the KV cache.

Other hardware that runs it

85Excellent quality (A+) · 85 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 Q6_K · 55.8 tok/s · Runs great
81Great quality (A) · 81 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3090 Q4_K_M · 42.0 tok/s · Runs great
81Great quality (A) · 81 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 Q4_K_M · 45.2 tok/s · Runs great
81Great quality (A) · 81 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX Q4_K_M · 37.1 tok/s · Runs great
86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell Q8_0 · 40.9 tok/s · Runs great
72Great quality (A) · 72 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4080 SUPER Q3_K_M · 42.7 tok/s · Runs well (tight fit)

Quick answers

How much memory does UI-Mate 27B need on the NVIDIA Jetson AGX Thor 128GB?

At Q5_K_M it needs about 29.8 GB. The NVIDIA Jetson AGX Thor 128GB has 115 GB usable.

How fast is UI-Mate 27B on the NVIDIA Jetson AGX Thor 128GB?

About 10.1 tok/s at Q5_K_M, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of UI-Mate 27B should I use on the NVIDIA Jetson AGX Thor 128GB?

Q5_K_M. Of the versions that fit, it is the one that runs best; when two run equally well, the check prefers the higher-rated one.

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.